Ternary Bonsai 2 27B
A ternary-quantized 27B-parameter language model released by PrismML in GGUF format, supporting PQ2_0 quantization.
Timeline (last 90 days)
PrismML released Ternary Bonsai 2 9B, whose GGUF file is only 2.25 GiB, while the 27B version is 6.70 GiB.
In laptop benchmarks, Ternary Bonsai 2 9B is 2.4–3.6 times faster than 27B.
The existing 27B production environment runs on llama.cpp, using PQ2_0 quantized weights, two parallel slots, a shared 32k context, temperature set to 0, and responses going through strict json_schema decoding.
In task A, after reweighting by production volume, the 9B's allow proportion dropped from the 27B's 86.4% to 49.5%, clarify rose from 13.4% to 50.1%, and the weighted agreement rate was 61.2%.
In task C, the 9B stayed consistent on 91 of the 103 cases the 27B marked as flagged or urgent, an agreement rate of 88.3%; but there were only five none cases, making it impossible to reliably estimate the false positive rate.
All Facts (5)
In laptop benchmarks, Ternary Bonsai 2 9B is 2.4–3.6 times faster than 27B.
50%UnverifiedThe existing 27B production environment runs on llama.cpp, using PQ2_0 quantized weights, two parallel slots, a shared 32k context, temperature set to 0, and responses going through strict json_schema decoding.
50%UnverifiedIn task A, after reweighting by production volume, the 9B's allow proportion dropped from the 27B's 86.4% to 49.5%, clarify rose from 13.4% to 50.1%, and the weighted agreement rate was 61.2%.
50%UnverifiedIn task C, the 9B stayed consistent on 91 of the 103 cases the 27B marked as flagged or urgent, an agreement rate of 88.3%; but there were only five none cases, making it impossible to reliably estimate the false positive rate.
50%UnverifiedPrismML released Ternary Bonsai 2 9B, whose GGUF file is only 2.25 GiB, while the 27B version is 6.70 GiB.
50%